Automated ECG segmentation with dynamic time warping

Author

Vullings, H.J.L.M. ; Verhaegen, M.H.G. ; Verbruggen, H.B.

Author_Institution

Dept. of Electr. Eng., Delft Univ. of Technol., Netherlands

fYear

1998

fDate

29 Oct-1 Nov 1998

Firstpage

163

Abstract

To detect an abnormal conduction of the heart, cardiologists annotate certain points in the electrocardiogram (ECG) manually. As this is a very strenuous task, several algorithms have been developed to segment the ECG automatically. In this paper, we describe several such methods, and we further present a new single-lead method based on dynamic time warping (DTW). The results are tested on the QT database and compared to Laguna et al.´s (1997) two-lead method. DTW produces a smaller mean error, but has a higher standard deviation than Laguna´s method

Keywords

bioelectric phenomena; dynamic programming; electrocardiography; medical signal processing; ECG annotation; Laguna´s two-lead method; QT database; abnormal heart conduction detection; automated ECG segmentation; cardiology; dynamic programming; dynamic time warping; mean error; single-lead method; standard deviation; Band pass filters; Cardiology; Clinical diagnosis; Databases; Dynamic programming; Electrocardiography; Heart; Hidden Markov models; Speech recognition; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Engineering in Medicine and Biology Society, 1998. Proceedings of the 20th Annual International Conference of the IEEE

Conference_Location

Hong Kong

ISSN

1094-687X

Print_ISBN

0-7803-5164-9

Type

conf

DOI

10.1109/IEMBS.1998.745863

Filename

745863